Optical switch with integrated fast protection function
By integrating fast optical switches and slow optical switches in high-port number mechanical optical switches, combined with cross-connection structure and automation mechanism, the problem of slow switching speed of optical switches in fault recovery and protection is solved, and the provision of fast protection and recovery services is achieved , reduces redundancy and cost, and improves scalability and reliability.
Patent Information
- Application Number
- CN202380027094.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2022-01-13
- Filing Date
- 2023-01-13
- Publication Date
- 2024-11-08
AI Technical Summary
Existing optical switches are slow in failure recovery and protection switching, which cannot meet the needs of fast protection and recovery services. At the same time, fast optical switches are costly and difficult to scale, and cannot meet the requirements of high port count and high availability.
Integrate fast optical switches into mechanical optical switches with high port counts, combine slow optical switch structures to achieve rapid protection and recovery services through cross-connection structures and automation mechanisms, separate configuration and fault recovery operations, and utilize redundancy and channel groups. Size the fast optical switch to reduce redundancy and reduce costs.
It realizes the provision of rapid protection and recovery services, reduces the configuration complexity and redundancy of optical interconnect services, improves the scalability and reliability of switching structures, reduces the number of redundant optical interconnects, and reduces the cost. .
Smart Images

Figure CN118923127A_ABST
Abstract
Description
[0001] CROSS-REFERENCE TO RELATED APPLICATIONS
[0002] This application claims the benefit of U.S. Patent Application No. 17 / 647,862, filed on January 13, 2022, the entire contents of which are incorporated herein by reference. Technical Field
[0003] The present disclosure relates generally to optical networks, and more particularly to optical switches. Background Art
[0004] Optical interconnect services within a data center or data center cluster (e.g., within a customer chassis and / or rack), for example, to process, store, and / or route network traffic between network resources, are typically provided using manual connections provided by large patch panels. Optical interconnect services can be at least partially automated by using large patch panel groups, where automation elements are used to automate connections to complete or remove optical circuits. Optical interconnects using mechanical switching (such as automation elements) may have optical switching speeds that are slow relative to the restoration or protection switching times required in the optical network. In contrast, optical interconnects using all-optical switching (such as beam steering technology) have fast optical switching times, making them suitable for protection switching or optical restoration. Data center switch structures can employ slow and fast optical switches to provide optical interconnect services with different levels and / or combinations of speed, performance, redundancy, protection, and / or reliability. Typically, fast switches are more expensive and cannot be scaled in size like slow switches. Summary of the invention
[0005] The present disclosure describes an optical switch that integrates a fast optical switch into a high-port-count mechanical optical switch to provide fast protection services. A large optical switch with one or more optical switches can provide a large number of ports and typically includes an automated or other mechanical device to switch input ports between various output ports. In one example, the optical switch includes a slow switch structure and a fast optical switch to provide fast protection services to an optical connection established on the slow switch structure. Relative to the slow switch structure, the fast optical switch can have a smaller number of input and output ports. The fast optical switch can be a photonic switch. The fast optical switch can rely on mechanical switching, microelectromechanical system (MEMS)-based switching, waveguide-based switching, or another type of optical switching. The fast optical switch of the optical switch can have a faster switching time relative to the slow switch structure of the optical switch. The switching time of the fast optical switch of the optical switch can be, for example, less than 1 second or 1000 milliseconds (ms), or less than 100 milliseconds, or less than 10ms.
[0006] In one example of an optical switch, the fast optical switch may have one or more output ports connected to corresponding output ports of the optical switch, the fast optical switch may have an input port connected to an output of a cross-connect structure of the optical switch, and the cross-connect structure may have an input connected to an input port of the optical switch. In another example of an optical switch, the fast optical switch may have one or more input ports connected to one or more output ports of the cross-connect structure, and the fast optical switch may have one or more output ports connected to one or more input ports of the cross-connect structure. Depending on the configuration of the cross-connect structure, different input ports of the optical switch may be selected for switching to the fast optical switch input.
[0007] Therefore, reconfiguring the fast optical switch to switch the input port from the first output port to the second output port can quickly redirect the optical signal received at the input port from the slow switch structure to a different optical path through the slow switch structure, thereby redirecting to a different output port of the slow switch structure. Therefore, the fast optical switch enhances the high port count and switching capability of the slow switch structure with the fast switching time of the fast optical switch.
[0008] The technology of the present disclosure includes one or more specific technical improvements, which provide at least one practical application in the field of computer network technology. As described herein, an optical switch including a fast optical switch connected to a slow switch structure of an optical switch and enhancing the slow switch structure can separate a relatively slow configuration / reconfiguration operation for an optical path from a relatively high-speed protection and / or recovery operation (such as switching failure from hardware / software) for the optical path. In some examples, the optical switch includes a fast optical switch that can be integrated into and / or encapsulated in the slow switch. Therefore, the optical switch can make the configuration and / or reconfiguration sequential and / or "slow" (e.g., using a mechanical and / or automated switching scheme) without significantly affecting and / or destroying the speed of protection and recovery. This can reduce the complexity of the configuration / reconfiguration of all optical interconnection services involving the optical switch and / or increase its reliability. The optical switch can improve the switch structure by enabling optical interconnection grouping using fast protection services (such as 1:1, 1:N, etc.), so that fast optical switching can be automatically triggered and / or based on signaling from a remote node location to trigger fast optical switching. Additionally, the size of the fast optical switch can be scaled based on the size of the channel group requiring redundancy and protection rather than the entire size of all optical interconnects, for example, enabling the use of smaller fast optical switches. In addition, the fast optical switch connected to the slow switch structure within the optical switch can enable optical interconnects that utilize fast optical switching speeds to be protected with a lower level of redundancy via the fast optical switch, for example, fewer redundant optical interconnects through the fast optical switch because the slow switch structure can be reconfigured to reroute around a failed fast optical switch interconnect. As another example, the slow switch structure of the optical switch can host facilities and resources for measuring and monitoring all optical paths, for example, including but not limited to by performing optical time domain reflectometer (OTDR) measurements, optical performance monitoring (OPM), bit error rate (BER) monitoring, etc.
[0009] In one example, the present disclosure describes an optical switch, comprising: a plurality of input ports and a plurality of output ports; a cross-connect structure having one or more inputs, one or more outputs, and a device for selectively cross-connecting the inputs with the outputs; an integrated fast optical switch, comprising a first input, a first output, and a second output, wherein the first input is connected to a first output among the outputs of the cross-connect structure, and wherein a switching time of the integrated fast optical switch is less than a switching time of the cross-connect structure and / or a slow switch to switch the first input between a first output on a path to a first output port among the plurality of output ports and a second output on a path to a second output port among the plurality of output ports.
[0010] In another example, the present disclosure describes an interconnect system comprising: a first data center interconnect; a different second data center interconnect; an optical switch comprising a plurality of input ports and a plurality of output ports; a cross-connect structure having one or more inputs, one or more outputs, and an automated mechanism for cross-connecting the inputs to the outputs; an integrated fast optical switch comprising a first input, a first output, and a second output, wherein the first input is connected to a first output among the outputs of the cross-connect structure, and wherein the fast optical switch has a switching time of less than 1000 milliseconds to switch the first input between a first output on a path to a first output port among a plurality of output ports and a second output on a path to a second output port among the plurality of output ports, wherein a first output port of the plurality of output ports is connected to the first data center interconnect, and wherein a second output port of the plurality of output ports is connected to the second data center interconnect.
[0011] In another example, the present disclosure describes a controller comprising: a processing circuit system coupled to a memory, the processing circuit system and the memory configured to control an optical switch including multiple input ports and multiple output ports; a cross-connect structure having one or more inputs, one or more outputs, and an automated mechanism for cross-connecting the inputs to the outputs; an integrated fast optical switch comprising a first input, a first output, and a second output, wherein the first input is connected to the first output of the cross-connect structure, and wherein the fast optical switch has a switching time of less than 1000 milliseconds to switch the first input between a first output on a path to a first output port among the multiple output ports and a second output on a path to a second output port among the multiple output ports.
[0012] In another example, the present disclosure describes a method, including: detecting, by a controller of an optical switch, a failure of a first data center interconnect connected to a first output port of the optical switch; and, in response to detecting the failure, outputting, by the controller of the optical switch, configuration data to configure a fast optical switch of the optical switch to switch from the first output port of the optical switch connected to the first data center interconnect to a second output port of the optical switch connected to a second data center interconnect.
[0013] The details of one or more examples of the technology of the present disclosure are set forth in the accompanying drawings and the following description. Other features, objects, and advantages of the technology will be apparent from the description and drawings, and from the claims. BRIEF DESCRIPTION OF THE DRAWINGS
[0014] Figure 1 is a block diagram illustrating an example interconnect system incorporating optical switches having slow optical switches and integrated fast optical switches in accordance with one or more techniques of this disclosure.
[0015] Figure 2Ais a block diagram illustrating an example switch including a fast optical switch and a slow optical switch, in accordance with one or more techniques of this disclosure.
[0016] Figure 2B is a block diagram illustrating an example switch including a fast optical switch and a slow optical switch, in accordance with one or more techniques of this disclosure.
[0017] Figure 3 is a block diagram illustrating another example switch including a fast optical switch and a slow optical switch as part of an optical network device, in accordance with one or more techniques of this disclosure.
[0018] Figure 4 is a block diagram illustrating an example protection scheme including fast optical switches and slow optical switches as part of an optical network device, in accordance with one or more techniques of this disclosure.
[0019] Figure 5 is a block diagram illustrating another example protection scheme including a plurality of fast optical switches and a slow optical switch as part of an optical switch, in accordance with one or more techniques of this disclosure.
[0020] Figure 6 is a block diagram illustrating an example protection scheme including a plurality of fast optical switches and a slow optical switch as part of an optical network device, in accordance with one or more techniques of this disclosure.
[0021] Figure 7 is a block diagram illustrating additional details of one example of a computing device that operates in accordance with one or more techniques of this disclosure.
[0022] Figure 8 is a flow chart of an example operating mode of an optical switch in accordance with one or more techniques of this disclosure.
[0023] Like reference numerals refer to like elements throughout the drawings and the specification. DETAILED DESCRIPTION
[0024] Network services provided to clients may have minimum quality of service (QoS) requirements. QoS protocols may at least partially determine the cost of the service and may dictate the underlying architecture and design of the network. QoS may specify a certain level of availability, speed, bandwidth, and / or other attributes for a network service. The availability of a service may be determined and / or influenced by the overall reliability of the underlying network elements and other external factors (such as fiber cuts, etc.). The reliability of a device may be characterized by a failure in time (FIT) rate, a mean time between failures (MTBF) value, etc. The availability of a service may also be determined and / or influenced by the time required to restore service after a device failure or other failure (such as physical fiber optic cable equipment and / or systems). For example, even if the overall reliability of a particular device or element is high, if the time required to restore service is long, the availability may be low.
[0025] Large automated switches are used to provide cross-connection or configuration services and can have a low failure rate. Automated switches can maintain the existing switch state even in the event of a power or equipment failure. For example, when such a failure occurs, the existing optical connection is not affected and the availability of the existing optical connection may not be affected, and only new services can be added or removed in this case. Such switches may be referred to as "slow optical switches" in this article.
[0026] In contrast, fast optical switches may be used to provide protection services and may have a low failure rate. However, in the event of a failure, the mean time to restore service with a fast optical switch may be long, for example, because all connections through the switch may have to be disconnected, the switch may have to be replaced with a new switch, and all connections may have to be reconnected. In the event of a power or equipment failure, a fast optical switch may not be able to maintain its current connection state and / or switch configuration. For example, a fast optical switch will not passively provide switching in the absence of power, and all services through a failed fast optical switch may be affected. The larger the fast optical switch, the greater the impact of the failure on service.
[0027] Conventionally, improving the reliability and / or availability of protection services provided by independent fast optical switches requires additional strengthening of power supplies and power backup, switch redundancy to meet availability requirements, and also requires expanding the fast optical switches to the largest possible size when or before the fast switches are first used (e.g., “day one”) because the fast optical switches are used for both configuration and protection.
[0028] Fast optical switches may be deployed in pairs (e.g., redundant pairs), and all protected services may need to be duplicated, while lower levels of protected services (e.g., M:N, etc.) may not be feasible. Redundancy can be used to reduce the time used to restore a failed component. Typically, only single component failures are considered, and it is assumed that the probability of two components failing simultaneously is not high. Replacing a fast optical switch involves disconnecting all inputs and outputs of the failed switch and reconnecting them to another switch, such as a manual operation, and takes many hours to complete, and it is expensive to keep a spare (e.g., currently unused) large fast optical switch. For example, the time used to restore a fast optical switch may be about 30 seconds per connection. A relatively small 48-port fast optical switch may have a maximum restoration time of about 24 minutes and an average restoration time of about 12 minutes (e.g., only a portion of the ports may need to be restored). A relatively large 384-port fast optical switch may have a maximum restoration time of about 192 minutes and an average restoration time of about 96 minutes. However, depending on the QoS agreement, the maximum annual downtime allowed may be 60 minutes or less, or even 1 minute or less. The maximum annual downtime of an independent fast optical switch with 99% availability is about 3.7 days, the maximum annual downtime of 99.9% availability is about 8.8 hours, the maximum annual downtime of 99.99% availability is about 52.6 minutes, and the maximum annual downtime of 99.9999% availability is about 31.5 seconds. For example, an independent fast optical switch needs 99.9999% availability to provide a QoS of less than one minute of annual downtime. Therefore, independent fast optical switches are currently unable to meet such QoS requirements and usually require redundancy to provide such services.
[0029] Fast and slow optical switches include different tradeoffs. For example, slow optical switches may be less expensive, more scalable, and include the ability to maintain the interconnect during a power outage compared to fast optical switches. Fast optical switches may be able to achieve switching speeds that slow optical switches cannot, for example, provide faster services and provide optical interconnect protection by fast optical switching to redundant optical interconnect paths.
[0030] Cross-connections between optical clients within or between data centers can be provided by large automated optical patch panel switches. Optical patch panel switches can be automated by automated mechanisms to configure or reconfigure patch panels in sequence or a few ports at a time. The time required to provide or cancel service using an automated patch panel is usually slow, on the order of seconds and / or minutes, and large automated patch panels can be referred to as slow optical switches. Slow optical switches can be extended to large port counts, such as thousands of ports. For example, over a period of time, the size of a slow optical switch can be gradually expanded from a first port count (e.g., two thousand simplex ports) to a second port count and a higher port count (e.g., six thousand simplex ports). In other words, slow automated switches can be scaled up and built in a distributed manner. In addition, variable optical attenuation (VOA) and power monitoring options can be built into slow optical switches, however, slow optical switches do not require optical feedback to work. The cost per port of a slow optical switch is lower than that of a fast optical switch, for example, in some cases less than half of a fast optical switch, and a slow optical switch does not require power to maintain the cross-connect state. Slow optical switches require power to operate, for example, by switching connections of an automated mechanism, but can passively maintain current connection states. Optical cross-connect services using slow optical switches are typically used for cross-connects within a data center or cluster of data centers that are close to each other, for example, within the same campus or within an area such as a metropolitan area.
[0031] Direct, dedicated, carrier-grade network links between clients may be distributed over a wide geographic area and use dense wavelength division multiplexing (DWDM) optical transponders to transport data, and may include multiple types or categories of transport services with varying levels of reliability and availability. For example, transport services may include unprotected services, protected services, and dual-diversified services. Service provisioning, organization, protection, and restoration using optical switches can be automated, which may require switch response times to be fast to meet fault mitigation or restoration requirements, and may also require individual switch reconfiguration times to be fast. These types of services can be run at multiple data center locations in data centers across multiple sites in a metropolitan or regional optical network. In other words, provisioning and automating services between data centers in larger metropolitan or regional groupings may require fast optical switches, for example, with response times of less than 1000ms.
[0032] Current cross-connect architectures for optical switching and restoration rely on an optical network that includes fast optical switches to reroute and / or protect services when a failure occurs in the optical network, such as a fiber cut, a common equipment failure (e.g., power), or a transmission equipment failure (e.g., source and sink). Optical switching and / or restoration may require fast optical switches with a response time of less than 1000 milliseconds. In some cases, optical protection such as one-to-one switching, one-to-N switching, etc. may require a switching time of less than 10ms. In some cases, the response time for a single switching event of a fast NxN optical switch may be in the millisecond range, with a full reconfiguration response time of less than 100ms or less than 10ms. Fast optical switching times are required to prevent higher layers in the stack, such as higher L3 to L7 open systems interconnection (OSI) layers, from detecting the failure condition and triggering corrective actions. In addition, fast optical switching times may be required to minimize network connection interruption time (e.g., in order to meet quality of service (QoS) requirements) and save cost, space, and power by reducing the need for redundant and expensive transmission equipment.
[0033] For example, client signals may originate from different client platforms and are received at the optical network from various sources (e.g., routers, other switches, data center interconnects (DCIs), etc.). The optical network may receive client traffic at 10G, 100G, 400G, or other rates. Incoming client traffic may also have different service classes and QoS requirements, such as unprotected, protected, or dual diversified. The number of clients that the optical network can serve can range from up to one thousand (at 100G speeds) to several thousand (e.g., at 10G speeds). The optical network of NxN optical switches can switch the incoming client signal to any DCI port, and the DCI port can adjust / map the client signal to a DWDM signal. The DWDM signal can then be transmitted over a line system to another node in another data center or location. The network / domain controller can provide signaling and control functions that allow the system (e.g., including fast switching optical networks) to perform functions such as: service-agnostic allocation of DCI and DWDM channels, service management across multiple optical networks and different networks, decomposition of optical networks, detection and mitigation of failures by rerouting client signals from paths with failed elements to other working paths in the network, use of spare capacity (e.g., ports, switches) to improve network reliability and availability, network optimization and defragmentation, and zero-touch automatic provisioning and reconfiguration of client paths.
[0034] Examples of current fast optical switches and optical switching technologies include beam steering technologies such as electro-optical, acousto-optical, magneto-optical, thermo-optical, or micro-electromechanical technologies. Fast optical switches can be configured to perform multiple cross-connections simultaneously, and can have a switch response time of less than 10ms or less than 1ms, and complete reconfigurability in less than 100ms or less than 50ms. VOA and power monitoring options can be built into fast optical switches. Fast optical switching response times enable fast optical switches to provide layer 0 and layer 1 protection and / or restoration services that can preempt connection fault detection and / or corrective measures at higher layers. Fast optical switching response times can also enable network flexibility and reconfigurability, for example, by reconfiguring router / repeater ports in response to changes in network demand over time, or reducing the interruption time of failures in other parts of the network. Current fast optical switches are limited to 1200 simplex ports or less.
[0035] However, current fast optical switch technology is limited by switch density and / or port count size, high cost per port, and fast optical switches themselves are single points of failure, which require redundancy and / or other expensive mechanisms to improve reliability. In addition, the cost of scaling current fast optical switch technology to higher switch densities (to the extent that scaling is possible) increases exponentially. In addition, current fast optical switch technology is generally unable to maintain current optical interconnects in the event of a power failure, for example, in contrast to certain slow optical switches. Fast optical switches are unable to maintain current optical interconnects passively (e.g., without power), which places additional requirements on the power supply, such as the need for power redundancy and the need for integrated external battery backup in the event of a power failure.
[0036] For example, if any failure occurs in the optical mechanism of the current fast optical switch, the fast optical switch needs to be completely replaced and essentially all ports are completely disconnected and reconnected to the new fast optical switch. Replacing a failed fast optical switch is manual and can take hours. While the fast optical switch itself may have very high reliability, a fast optical switch failure may cause a long service failure. Therefore, redundant fast optical switches can be deployed at each site, with half of the services configured through one switch and the other half through the other switch. All protected services require the same level of reliability and a redundant pair of client signals.
[0037] Furthermore, because today's fast optical switches cannot be removed once they are in service without affecting availability, the largest possible switches must be deployed to maximize the ability to operate on all channels. In other words, the largest possible switches must be deployed on "day one." Therefore, all classes of services, both unprotected and protected, need to be added via fast optical switches to optimize the entire traffic flow. This increases the unit cost for all service classes. Additionally, it is difficult or impossible to take advantage of future technology improvements in fast optical switching technology, e.g., speed, size, etc., or to take advantage of a "pay as you grow" model (e.g., by incrementally increasing the number of ports rather than completely replacing with a larger switch) without downtime or service impact.
[0038] The present disclosure describes technologies for network switching and network switches including an optical switch that integrates a fast optical switch into a high-port-count mechanical optical switch (hereinafter, also referred to as a "slow optical switch" or "slow switch structure"). The slow switch structure and one or more fast optical switches can be combined in a single chassis of the optical switch.
[0039] In some examples, the techniques described herein can be configured to utilize a large port count optical cross-connect mesh structure (e.g., an automated patch panel) and use integrated fast optical switches to provide protection and restoration services within a slower and larger automated automated patch panel. The techniques described herein can combine the advantages of slow optical networks (such as for connecting services within or between data centers) with the advantages of fast optical switches (e.g., for providing provisioning and automation services between data centers in larger metropolitan or regional groupings). For example, these techniques can provide large-scale and low-cost automated optical patch panels used in data centers to provide and manage cross-connect services while allowing fast optical switches to operate on subsets of channels / connections to provide high-availability services. In some examples, the technology can reduce and / or eliminate the trade-offs of utilizing fast optical switch technology with slow optical switch technology, for example, by offsetting the limitations of each technology with the advantages of the other technology, as described below.
[0040] In some examples, the techniques described herein can enable configuration and reconfiguration of all services provided by a mesh fabric to be slow and sequential while still providing fast interconnection speeds, for example, while still providing protection and restoration capabilities. A fast optical switch coupled to a slow optical switch within an optical switch can improve the scalability of the switch fabric. In some examples, not all services in an optical network require fast optical switching response times. Encapsulating a fast optical switch within a slow optical switch, for example, integrating the fast optical switch within a cross-connect fabric, can enable grouping of optical interconnects, for example, based on speed, protection, etc., which can enable autonomous and / or remote control of provisioning and / or re-provisioning of optical interconnects between fast and slow services, rather than using fast and slow optical switches in parallel and / or in series.
[0041] For example, these techniques can enable expansion of the number of ports and / or density of fast and slow optical switches based on group size and at a lower cost. If the demand for fast optical switching speeds increases, the slow optical switch can be expanded and another fast optical switch can be used to enhance the larger slow optical switch, which has a lower overall cost than expanding the fast optical switch, for example, even if the slow optical switch does not need to be expanded to accommodate the enlarged (and more expensive) fast optical switch.
[0042] In some examples, these techniques can improve the scalability and cost of switch fabrics by reducing the number of redundant optical interconnects through fast optical switches that need to be protected (e.g., opening these ports for other optical interconnects). For example, redundant optical interconnect paths of fast optical switches can be rerouted around a failed fast optical switch through a slow optical switch.
[0043] Additionally, in some examples, these techniques can reduce the complexity and cost of the mesh structure by enabling measurement and / or monitoring of fast optical switches and slow optical switches through resources hosted by the slow optical switches (e.g., OTDR measurement, OPM monitoring, BER monitoring, etc.). For example, a slow optical switch port can be used for monitoring and diagnosis, thereby opening up a fast optical switch port that would otherwise be used for monitoring and diagnosis.
[0044] The technology disclosed herein may include a network and a programmable network platform that performs operations of a resource switching controller to allocate ports and cross-connections on a mesh structure, the mesh structure including an optical network device with a fast optical switch for enhancing a slow optical switch to form an optical sub-network, allocate network resources, including fast optical switches connected to the optical mesh structure, automate network services, including provisioning, troubleshooting and reconfiguration, and arbitrate services between multiple locations within a data center, between data centers, or between multiple data centers. For example, the switching controller may be configured to allocate ports on a slow optical switch and a fast optical switch to form an optical sub-network, including at least one optical cross-connection configured to be switched by a fast optical switch, and the network switching controller may be configured to reallocate at least one optical cross-connection of the sub-network to at least one redundant optical cross-connection that bypasses the fast optical switch. The optical sub-network can be used to provide optical protection against network element failures or fiber failures, for example, by providing head-end and tail-end switching to automate the setup and troubleshooting of network components and subsystems, and provide dynamic reconfiguration and allocation of network resources.
[0045] Figure 1 is a block diagram illustrating an example interconnection system incorporating an optical switch having a slow optical switch and an integrated fast optical switch. According to one or more techniques of the present disclosure. Interconnection system 2 depicts interconnection facilities 8A to 8B (collectively, "interconnection facilities 8") operated by an interconnection system provider, interconnection facilities 8 connected by an optical network 10 that can be configured to cross-connect client networks 6A to 6B (collectively, "client networks 6"). In some cases, each client network 6 may be associated with a different customer of the interconnection system provider. In some cases, client networks 6 are all associated with a single customer of the interconnection system provider. As used herein, the term "customer" of an interconnection system provider may refer to a tenant of an interconnection facility 8 deployed by an interconnection system provider, whereby a customer rents space within the interconnection facility 8 in order to co-locate with other tenants, thereby improving the efficiency of independent facilities, and interconnecting network equipment with network equipment of other tenants within the interconnection facility or campus to reduce latency / jitter and improve reliability, performance, and security relative to the transmission network, etc. An interconnection system provider may be referred to as an interconnection facility provider in some cases because they are generally the same entity.
[0046] Each interconnection facility 8 may represent a different data center in a geographically distinct metropolitan area to provide a resilient and independent interconnection service exchange through which customers in one metropolitan area and customers in a different metropolitan area may connect to receive and provide services respectively.
[0047] In each interconnect facility 8, space may be divided and rented in flexible increments to customers in the form of cages (areas of common building space surrounded by fences or other dividers), cabinets, racks, suites (enclosed rooms that are not part of the common building space), or other spaces in which customers may place their network equipment to provide and / or receive network services to / from other customers located in the same interconnect facility 8 and / or other customers located in another interconnect facility 8.
[0048] The optical network 10 (including the optical switch(es) 12) represents an optical and photonic switching infrastructure that is configured by the programmable network platform 3 to create a fiber cross-connect 7 that connects a client network 6A and a client network 6B located in interconnection facilities 8A and 8B, respectively. The optical network 10 may include pre-installed optical fiber between the client network 6 and at least one distribution facility (or "distribution rack") of the interconnection facility 8, and may also include pre-installed optical fiber between multiple distribution facilities of the interconnection facility 8. The optical network 10 may also include programmable photonic switches located within the distribution facilities of the interconnection facility 8 and / or located at customer space demarcations in the interconnection facility 8. Although described herein as dynamically configurable, much of the optical network 10 may be statically configured by a network operator associated with an interconnection facility provider, a network service provider, or other entity that manages aspects of the optical network.
[0049] The optical network 10 may include one or more optical network devices 4, such as DCI repeaters, muxponders, optical transceivers, channel multiplexers / demultiplexers, amplifiers, and / or optical switches, such as wavelength selective switches (WSS), photonic cross-connects (PXC), optical cross-connects (OXC), optoelectronic-based switches (OEO), or other types of devices that switch optical signals. The optical switch may route optical signals (light beams or wavelengths) between optical fibers coupled to the optical switch.
[0050] The system 2 also includes a programmable network platform (PNP) 3, alternatively also referred to herein as an "interconnection platform". The programmable network platform 3 can open a software interface that defines methods, fields, and / or other software primitives through which (multiple) applications 15 can call the PNP 3 to dynamically provide a fiber cross-connect 7 between the client networks 6A, 6B. In this way, the PNP 3 allows customers, operators, network service providers (NSPs), and / or interconnection system providers themselves to have the programmable ability to configure the optical network 10 to interconnect the client network 6A to the client network 6B using the fiber cross-connect 7.
[0051] Programmable network platform 3 may represent an application program executed within one or more data centers of system 2, or alternatively, an application program executed off-site / remotely, for example, at a back-end or branch office of a provider of interconnected system 2. Programmable network platform 3 may be distributed in whole or in part in an interconnection facility. Figure 1 As shown, the programmable network platform 3 can control the service provision of multiple different interconnection facilities. Alternatively or additionally, multiple independent instances of the programmable network platform 3 can control the service configuration for the corresponding multiple different interconnection facilities.
[0052] The application(s) 15 represent at least one application that communicates with the PNP 3 to request and dynamically provide interconnection between the interconnection facilities 8 of the client networks 6A, 6B. The application 15 represents client software for interacting with the PNP 3 and may include a customer portal, a customer application, an interconnection system 2 provider application accessible only to an operator of the interconnection facility 8, a console such as a command line interface or a graphical user interface. Users or clients of the application(s) 15 may include enterprise customers, cloud service and content providers, carriers, network service providers (NSPs), and / or the interconnection system providers themselves.
[0053] One of the application(s) 15 may issue an interconnect request 11 to the PNP 3 that specifies parameters for interconnecting between the interconnection facilities 8 of the client networks 6A and 6B. In response to receiving the interconnect request 11, the PNP 3 determines a path for interconnection, such as a lightpath through the optical network 10, and dynamically provides a path for interconnection with the optical fiber cross-connect 7 in the optical network 10 to provide an optical fiber-based interconnection between the client networks 6A, 6B to satisfy the interconnect request 11. Example parameters for the interconnect request 11 may include requested bandwidth, service type (e.g., protected, unprotected, dual diversified, etc.), port identifier, etc.
[0054] The PNP 3 configures elements of the optical network 10 by issuing configuration commands to the elements within the optical network 10, either directly to the elements within the optical network 10 through the configuration interfaces of the elements, or indirectly to such elements through a software defined networking (SDN) controller (e.g., an SDN controller) that manages the elements on behalf of the PNP 3. In some cases, the PNP 3 may alternatively be referred to as a coordinator because the PNP 3 coordinates one or more SDN controllers to configure the optical network devices 4 (e.g., photonic switches) and / or other elements of the optical network 10 to establish the optical fiber cross-connections 7.
[0055] The programmable network platform 3 configures the optical network device 4 to switch optical signals along optical paths, each optical path starting from an optical transmitter and terminating at an optical receiver, and each optical transmitter and optical receiver are associated with one of the client networks 6. In this way, the client network 6 can exchange frames and packets of L0 / L1 / L2 / L3 services through dynamically provided optical fiber cross-connections. The optical path may also be alternatively referred to as an optical path, optical path, wavelength or optical transport network wavelength, or a composite DWDM optical signal. Example bandwidths for cross-connected optical paths may include, for example, 2.5Gbps, 10Gbps, 40Gbps, 100Gbps, 400Gbps or even multi-terabit DWDM optical signals. The optical fiber may include multiple optical paths, that is, the optical fiber can transmit optical signals of multiple optical paths as different wavelengths. Optoelectronic-based switches may limit switch applications according to the data rates, protocols, and formats supported by the electronic components of the switch.
[0056] The fiber cross-connect 7 may represent a layer 0 ("L0") connection, as the fiber cross-connect is the basis of the open systems interconnection (OSI) model or the TCP / IP model for packet networks. Specifically, the fiber cross-connect 7 may be the basis of the optical transport network (OTN) layer, which (typically in conjunction with the SONET / SDH layer) provides a layer 1 ("L1") connection between optical network devices 4 (such as wavelength division multiplexing (WDM) devices). For example, the fiber cross-connect 7 may represent one or more wavelengths (or "lambdas") that are photonically switched by elements of an optical switch structure to provide an optical path (or "lightpath") for optical signals exchanged between client networks 6A, 6B associated with different customers / tenants of the provider of the interconnection system 2. In this manner, the optical network 10 is configured to provide non-blocking switching through high-speed fiber connections between respective client networks 6A, 6B of customers of the provider of the interconnection system 2, and in doing so may provide reliable and low-latency communications between the client networks 6A, 6B.
[0057] The client networks 6A, 6B access the fiber cross-connect 7 using corresponding access links 9A, 9B to exchange data. The access links 9A, 9B may represent gray links / optical systems in some cases, where routers or switches of the client networks 6A, 6B exchange gray (colorless) optical signals with coherent optical devices, which convert between gray optical signals and optical signals of specific wavelengths (colors) exchanged with optical network devices of the optical network 10. In some examples, the pluggable coherent optical devices may be directly integrated into the optical network devices (e.g., the faceplates of the optical network devices), thereby eliminating the need for short-distance optical pluggable modules.
[0058] In some cases, the fiber cross-connects 7 may be the basis for layer 2 ("L2") or layer 3 ("L3") services provided by the interconnection system 2 provider to interconnect the client networks 6A, 6B according to the L2 or L3 services. For example, the interconnection facility 8 may operate a network service exchange, such as an Ethernet exchange and an Internet exchange and / or a cloud exchange, and each exchange may utilize dynamically provisioned fiber cross-connects 7 to transport L2 / L3 packet data between the client networks 6A, 6B.
[0059] According to the techniques described in the present disclosure, the optical network 10 includes at least one optical switch 12. The optical switch 12 includes a fast optical switch and a cross-connect structure (or "slow optical switch"). The fast optical switch can be integrated into the slow optical switch to form the optical switch 12. The optical switch 12 can be programmable and located in the distribution facility of the interconnection facility 8A and / or 8B. In some examples, the slow optical switch of the optical switch 12 can include an automated mechanism to switch the connection state of the connection port, and the fast optical switch of the optical switch 12 can be integrated into the slow optical switch and can include a switching time of less than 1000 milliseconds. The fast optical switch of the optical switch 12 can have one or more input ports connected to one or more output ports of the slow switch structure, and the fast optical switch can have one or more output ports connected to one or more input ports of the slow switch structure. The optical switch 12 can represent an optical distribution panel switch of a distribution panel of a client cage for hosting a client network 6A within the interconnection facility 8A.
[0060] As a result of providing fiber cross-connects 7 between interconnect facilities 8A and 8B through optical switches 12, the technology can provide a large port count optical cross-connect mesh structure, such as an automated patch panel, combined with protection and restoration services that use integrated fast optical switches to enhance slower and larger automated optical cross-connect mesh structures. Additionally, the optical network 10 including the optical switches 12 can provide scaling of the port number and / or density of fast and slow optical switches based on group size, reduce the number of redundant optical interconnects through fast optical switches, and enable measurement and / or monitoring of fast and slow optical switches through resources hosted by the slow optical switches, such as OTDR measurements, OPM monitoring, BER monitoring, etc. More details of optical cross-connects can be found in U.S. Patent Application No. 14 / 937,787 filed on November 10, 2015, which is incorporated herein by reference in its entirety.
[0061] Figure 2A2 is a block diagram illustrating an example optical switch 12 including a fast optical switch 204 and a slow optical switch 202, in accordance with one or more techniques of this disclosure. The fast optical switch 204 may be integrated and / or packaged within the slow optical switch 202, in that an input port of the fast optical switch 204 is connected to an output port of the cross-connect structure 203, and multiple output ports of the fast optical switch 204 are connected to different input ports of the cross-connect structure 203 or different output ports of the optical switch 12. At least some outputs of the cross-connect structure 203 are connected to output ports of the optical switch 12. At least some inputs of the cross-connect structure 203 are connected to input ports of the optical switch 12. In some examples, an optical interconnect facilitated by the optical switch 12 may include a path through the slow optical switch 202 that bypasses the fast optical switch 204, but an optical interconnect including a path through the fast optical switch 204 may not bypass the slow optical switch 202.
[0062] The client flow devices 212 may include customer premises routers, switches, WDM plugs, and / or any suitable devices for sending and / or receiving client optical network traffic. The client flow devices 212 are communicatively coupled to the optical switch 12 and are configured to send and receive network traffic through the optical switch 12. In some examples, the client flow devices 212 may be connected to each other and / or to the DCI layers 234-236 through an optical switch structure (e.g., such as the optical network 10 described above) including the optical switch 12. In the illustrated example, all of the client flow devices 12 are communicatively coupled directly to the optical switch 12, and more specifically, to the slow optical switch 202. In some examples, a portion of the client network traffic optical data path routed through the optical switch 12 includes only the slow optical switch 202, while a portion of the client network traffic optical data path routed through the optical switch 12 includes the slow optical switch 202 and the fast optical switch 204. The client traffic may be 10G, 100G, 400G, or any suitable network traffic speed, and the number of client services / devices of client traffic devices supported and / or routable through the optical switch 12 may be in the hundreds and / or thousands (e.g., at higher speeds such as 100G, 400G, etc.), and / or in the thousands or tens of thousands (e.g., at lower speeds such as 10G, 100G, etc.).
[0063] The slow optical switch 202 can be substantially similar to the slow optical switch described herein, for example, as described above with reference to Figure 1The slow optical switch 202 may be an optical patch panel that is automated by an automation mechanism to configure or reconfigure the patch panel sequentially or for a few ports at a time. In some examples, the slow optical switch 202 may be configured to switch network connections, for example, switching between ports, wherein the switching time for each port is greater than one second. The slow optical switch 202 may be extended to a large number of ports, for example, thousands of ports, tens of thousands of ports or more. The slow optical switch 202 may gradually expand from a first number of ports to a second number of ports, or even a higher number of ports, over a period of time. In some examples, power monitoring and VOA options may be built into the slow optical switch 202. The slow optical switch 202 may not require optical feedback to operate, and may not require power to maintain a cross-connection state. The slow optical switch 202 may require power to operate, for example, to switch connections by an automation mechanism, but may passively maintain the current connection state. For example, the slow optical switch 202 may be configured to maintain an interconnection state and / or configuration during a power cycle and / or switch failure. In some examples, the switch components and / or hardware (e.g., including a robotic arm) can be modular and can be configured to be replaceable in the field, for example, without interrupting part or any of the network traffic routed through the slow optical switch 202. In some examples, the optical switch 12, the slow optical switch 202, and / or the controller 240 can be configured to capture the switch state and / or configuration, for example, in a database or redundant database. The optical switch 12, the slow optical switch 202, and / or the controller 240 can be configured to then restore the switch state and / or configuration based on the captured switch state and / or configuration, for example, after a fault, failure, or other condition that requires resetting part or all of the optical switch 12 and / or the slow optical switch 202.
[0064] In some examples, the slow optical switch 202 can be configured to provide a mechanism to operate on all network traffic routed through the optical switch 12. In some examples, the slow optical switch 202 can be a single switch, while in other examples, the slow optical switch 202 can include a plurality of distributed slow optical switches with interconnections therebetween. In some examples, the per-port cost of the slow optical switch 202 can be less than the per-port cost of the fast optical switch 204.
[0065] The fast optical switch 204 can be substantially similar to the fast optical switches described herein, for example, as described above with reference to Figure 1The fast optical switch 204 can be integrated into the slow optical switch 202, for example, each input port of the fast optical switch 204 can be connected to at least one output port of the slow optical switch 202, and each output port of the fast optical switch 204 can be connected to at least one input port of the slow optical switch 202. The fast optical switch 204 can include a switching time of less than 1000ms. The fast optical switch 204 can include any suitable fast optical switching technology and / or fast beam steering technology, such as electro-optical, acousto-optical, magneto-optical, thermo-optical or micro-electromechanical beam steering. The fast optical switch 204 can be configured to perform multiple cross-connections simultaneously, and can have a switch response time of less than 10ms or less than 1ms, and complete reconfigurability in less than 100ms or less than 50ms. VOA and power monitoring options can be built into the fast optical switch 204. The fast optical switch 204 may have a response time that enables the fast optical switch 204 to provide protection and / or restoration services for Layer 0 and Layer 1 that can preempt higher layer connection failure detection and / or corrective actions. The fast optical switch 204 may have a response time that enables the network to be flexible and reconfigurable, for example, by reconfiguring router / repeater ports in response to time-dependent changes in network demand, or to reduce outage time when other parts of the network fail.
[0066] In some examples, the fast optical switch 204 may include a single fast optical switch, while in other examples, the fast optical switch 204 may include a plurality of fast optical switches, for example, a plurality of fast optical switches with a smaller number of ports. The fast optical switch 204 may have any suitable number of ports, however, the fast optical switch 204 may have a relatively small number of ports, for example, 1,200 ports or less. For example, the optical switch 12 may be scalable and may be configured to increase the number of ports supporting fast optical switching by increasing the number of fast optical switches 204 integrated within the slow optical switch 202 rather than packaging and / or integrating fast optical switches with a larger number of ports. For example, the cost per port of a fast optical switch may increase nonlinearly (e.g., exponentially) with the number of ports, and the fast optical switch 204 may be configured to have a relatively small number of ports to allow the optical switch 12 to increase the fast optical switching capacity by increasing the number of smaller, lower-cost fast optical switches 204.
[0067] In some examples, the optical switch 12 can be configured to reduce the size and / or port count of the fast optical switch 204, for example, while providing the same level of fast optical switching service. For example, the optical switch 12 can utilize an M:N (where M is less than N) protection scheme, where M ports are used to provide redundancy for N clients, and M+N ports must be located on the same fast optical switch 204. In some examples, M+N is less than 12 or 24, and multiple smaller fast optical switches 204 are integrated with the slow switch 202, enabling fewer and smaller fast optical switches 204 to be used for redundancy, and enabling hot standby of the fast optical switches 204.
[0068] In some examples, the slow optical switch 202 may be a larger optical mesh structure including an automatic patch panel for providing cross-connect services within a data center. The fast optical switch 204 may be used to provide protection and restoration services to a subset of services originating from or terminating in a data center. In the example shown, the optical switch 12 is communicatively connected to multiple DCI layers, for example, DCI layers 234-236. In some examples, the optical switch 12 may be communicatively connected to more or fewer DCI layers, or multiple DCI layers may be configured and / or grouped as a single DCI layer to connect to the optical switch 12. In some examples, the DCI layer and / or WDM layer nodes and / or optical fibers may be part of a shared risk group. For example, the DCI layer 234 may include a first shared risk group including multiple network traffic paths, for example, a first plurality of nodes and optical fibers, and the DCI layer 236 may include a second shared risk group including multiple network traffic paths, for example, a second plurality of nodes and optical fibers different from the first plurality of nodes and optical fibers. The risk of network traffic interruption and the time for recovery may be reduced by sharing risk grouping.
[0069] The DCI layers 234-236 may be configured to connect between data centers, for example, to connect the optical switch 12 to one or more devices located in a different data center and / or region than the optical switch 12, such as in another room, another building, another city, another region, or any other suitable data center site separate from the data center where the optical switch 12 is located. In some examples, the optical switch 12 may be located in a single location, for example, within a data center within a building. In other examples, the optical switch 12 may be distributed across multiple locations, for example, within a data center containing multiple buildings, or within a data center cluster.
[0070] In some examples, the optical switch 12 may include measurement and / or monitoring services. In the example shown, the optical switch 12 is communicatively connected to a measurement device 232. The measurement device 232 may include a power meter, an OTDR, a BER monitor, etc. The switch 12 may be configured for quality of service measurements. For example, the controller 240 may be configured to receive data and / or measurements from the measurement device 232 and determine a quality of service parameter of the switch 12.
[0071] In some examples, client network traffic from and / or to the client flow device 212 may be routed to the fast switch 204 via the slow switch 202, or client network traffic from and / or to the client flow device 212 may be rerouted only through the slow switch 202. For example, the optical switch 12 may be configured to support an optical sub-network configured to use a fast optical switch 204 integrated within the slow switch 202. In some examples, the optical switch 12 is configured to provide all services through the slow switch 202, and only ports and / or clients that require fast optical switching services (e.g., optical protection services, etc.) need to be part of the optical sub-network that includes the fast optical switch 204. Network traffic services that require fast switching capabilities may be routed through the fast optical switch 204, while network traffic services that do not require fast switching capabilities may be routed only through the slow switch 202. In some examples, one or more client network traffic routes may be rerouted through the slow switch 202, for example, for protection through redundancy. In other words, the optical switch 12 may provide network traffic fast network interconnect protection through redundancy without routing one or more redundant network traffic paths through the fast switch. For example, providing a redundant network traffic path for the fast optical switch 204 through the slow optical switch 202 may allow the fast optical network switch 204 to be reset without interrupting the fast optical service. In some examples, the optical switch 12 may be configured to provide a redundant network traffic path for the fast optical switch 204 through the slow optical switch 202, thereby reducing the reconfiguration time required to bypass a failed or faulty fast optical switch, for example, from hours to minutes.
[0072] In some examples, the optical switch 12 can enable seamless replacement and / or upgrade of the fast optical switch 204, or can enable seamless addition of other fast optical switches integrated within the slow optical switch 202, for example, additional fast optical switch network traffic routing can be added through the additional fast optical switches without interrupting current network traffic routing through the fast optical switch 204 and / or the slow optical switch 202. In some examples, the optical switch 12 can be configured to incorporate future technology improvements, for example, future fast and / or slow optical networking technologies, without interrupting current network traffic.
[0073] In some examples, the optical switch 12 can be configured to implement seamless service upgrades and downgrades. For example, the controller 240 can be configured to upgrade selected network traffic from a route that includes only the slow optical switch 202 to being routed only through the fast optical switch 204 without interrupting the selected network traffic and / or other network traffic. Conversely, the controller 240 can be configured to downgrade selected network traffic from a route that includes the fast optical switch 204 to being routed only through the slow optical switch 202 without interrupting the selected network traffic and / or other network traffic.
[0074] In some examples, the optical switch 12 can be configured to reduce port and switching costs. For example, the optical switch 12 can be configured to provide unprotected traffic through the slow optical switch 202 and bypass the fast optical switch 202, the optical switch 12 can be configured to reduce and / or eliminate the redundancy of the fast optical switch 204, for example, the redundancy can be provided by the slow optical switch 202. The optical switch 12 can be configured to allow multiple levels of protection, for example, protected, unprotected, through reconfigurable redundancy, and the optical switch 12 can be configured to improve the efficiency of the optical mesh structure by reducing the redundancy required within the fast optical switch 204, so that all ports in the system are addressable and reconfigurable.
[0075] The controller 240 is configured to operate on multiple nodes or domains. The controller 240 can be configured to integrate information from monitoring points, sensors, and switch ports, such as based on fault conditions. The controller 240 can be configured to allocate ports and cross-connections on the mesh structure, such as the optical switch 12, to form an optical sub-network. The controller 240 can be configured to allocate network resources connected to the optical structure, including slow optical switches 202 and / or fast optical switches 204, and automate network services, including provisioning, troubleshooting, and reconfiguration. The controller 240 can be configured to reallocate at least one optical cross-connection of a sub-network to at least one redundant optical cross-connection that bypasses the fast optical switch 204. In some examples, the controller 240 can be configured to arbitrate services in a data center, such as at a single location, multiple locations, and / or multiple locations distributed over a large geographic area. In some examples, the controller 240 may be configured to form one or more optical sub-networks within the optical grid including the optical switches 12 that may implement optical protection against network element or fiber failures, including features such as head-end and tail-end switching, automation of setup and troubleshooting of network components and subsystems, and dynamic reconfiguration and allocation of network resources. The controller 240 may represent Figure 1 The PNP 3 and / or one or more SDN controllers in the system.
[0076] Figure 2B is a block diagram illustrating an example switch 12 including a fast optical switch 204 and a slow optical switch 202 , in accordance with one or more techniques of this disclosure. Figure 2B The example switch 12 shown in FIG. Figure 2A The switch 12 in is basically similar, wherein Figure 2B Switch 12 in FIG. 1 shows an example of physical integration of the fast switch 204 with the slow switch 202 , for example, the physical mechanism and / or interconnection between the output port of the slow switch 202 connected to the input port of the fast switch 204 and the output port of the fast switch 204 connected to the input port of the slow switch 202 .
[0077] Figure 3 is a block diagram illustrating another example switch 312 including fast optical switch 204 and slow optical switch 202 in accordance with one or more techniques of this disclosure. Switch 312 may be similar to optical switch 12 described above, and illustrates multiple redundant network traffic paths 302a, 302b, 304a, and 304b.
[0078] In the illustrated example, the switch 312 is configured to provide network traffic routes 302a and 302b to connect between the client flow device 212 and the network paths A and B, and the network traffic routes 302a and 302b can be redundant with the network traffic paths 304a and 304b that provide fast optical switching between the client flow device 212 and the paths A and B. For example, the slow (e.g., automated) optical switch 202 can be configured to completely bypass the fast optical switch 204 to provide optical network traffic connections through the network traffic routes 302a and 302b, while the fast optical switch 204 can be replaced, reconfigured, and / or reset. In some examples, the slow optical switch 202 can also reroute the network traffic to a different fast optical switch 204, for example, an additional and separate backup fast optical switch 204 integrated within the slow optical switch 202. In some examples, multiple client inputs are not required to have fast optical switching protection services. In the example shown, routes A and B may be network traffic endpoints and / or nodes or intermediate points from which network traffic may be forwarded to an endpoint or branched to multiple endpoints.
[0079] Figure 4 is a block diagram illustrating an example protection scheme including a fast optical switch 204 and a slow optical switch 202 , in accordance with one or more techniques of this disclosure. Figure 4 A protection scheme is shown implemented using a switch 412, including a single fast optical switch 204 integrated with a slow switch 202. The switch 412 may be similar to the optical switch 12 described above.
[0080] In the example shown, the switch 412 can provide multiple network traffic protection types and / or levels, such as dual-diversified 412 network traffic, protected 414 network traffic, and unprotected 416 network traffic. The dual-diversified 412 network traffic and the unprotected 416 network traffic can be configured to bypass the fast optical switch 204. The size of the fast optical switch 204 may be limited only by the client signals that require fast protection or restoration service.
[0081] The switch 412 may be configured to provide protected transport services in the network. In the protected services, optical network paths may be switched based on the detection of path failures or DCI failures. The switch 412 may be configured to provide improved QoS and availability for all services, for example, by using excess network resources available in the network. In some examples, the switch 412 may be configured to share excess capacity between all services, which may reduce the cost of providing such services.
[0082] The switch 412 may be configured to implement protection and self-healing mechanisms. For example, the switch 412 may include protection against client plug, module, or rack failures. The switch 412 may be configured to use a protection scheme with additional network resources such as DCI modules, channels, etc. The switch 412 may be configured to implement shared redundancy, such as M:N (N>M) redundancy, which may reduce protection costs while increasing availability.
[0083] In addition to protection against node or device failures, switch 412 can also be configured for protection against fiber cuts and node failures. For example, switch 412 can be configured for 1:1 channel redundancy and separate node degrees and fiber paths from nodes. In a mesh network, fiber cuts may have different effects on different paths, and switch 412 can be configured to implement more complex protection and restoration schemes. Switch 412 can be configured to route and / or reroute network traffic during maintenance, upgrades, etc., thereby reducing network traffic interruptions and switch downtime.
[0084] In some examples, switch 412 may include an optical protection switch (OPS), such as a 1x2 switch. For example, switch 412 may be configured with OPS switching based on tail end detection, and may be configured to have a switching time of less than 50 ms. In some examples, switch 412 may include a grouped OPS, or a subset of a larger NxN fast optical switch, where the fast switching logic is built into the switch hardware and / or software. In some examples, switch 412 may be configured to bypass the OPS, such as in the event of a switch failure, and switch 412 may be configured to reroute traffic during maintenance, upgrades, etc., such as to reduce and / or minimize traffic disruption and / or downtime.
[0085] Figure 5is a block diagram illustrating an example protection scheme including a plurality of fast optical switches 702 - 706 and a slow optical switch 202 for an optical switch 512 , in accordance with one or more techniques of this disclosure. Figure 5 A protection scheme is shown implemented using switch 512. Switch 512 may be substantially similar to optical switch 12 and / or switch 412 described above.
[0086] In the example shown, the switch 512 can provide dynamic scalability and multiple protection types and / or levels for the optical mesh structure. In the example shown, each protected group AC can have the same or different protection types and / or levels. Clients using common protection resources are routed through the same fast optical switch, for example, all clients using protection resources grouped as protected group A are routed through fast optical switch 702, all clients using protection resources grouped as protected group B are routed through fast optical switch 704, and all clients using protection resources grouped as protected group C are routed through fast optical switch 706. In the example shown, the channels that are part of protected group AC are reconfigurable because they all flow through slow switch 202.
[0087] In the event of a fast switch failure, all channels in the group passing through the fast switch can be reconfigured to pass through a different or alternate switch. For example, protected group B can be routed through fast optical switch 702 or fast optical switch 706, for example, in the event of a failure of fast optical switch 704. In some examples, switch 512 is configured so that all client ports of switch 512 are reconfigurable.
[0088] For example, switch 512 may be configured to be reconfigurable to accommodate client port utilization, channel path requirements, changes in network traffic over time due to traffic churn and growth, changes in the relative mix of service types over time, and changes in customer requested service interfaces, such as from 10G to 400G data rates over one or more communications protocols such as Ethernet, Fibre Channel (FC), Synchronous Optical Network (SONET), Synchronous Digital Hierarchy (SDH), Optical Transport Network (OTN), etc. 512 may be configured to upgrade a service from unprotected to protected, or downgrade a service from protected to unprotected, in a matter of minutes with minimal or no disruption.
[0089] In some examples, switch 512 provides the advantage of routing all client traffic (including unprotected, protected, and dual-diversified services) through the same switch fabric, thereby enabling switch 512 to reconfigure, rebalance, or rearrange ports without physical intervention. In some examples, switch 512 is configured to optimize the flow of all network traffic (including different network traffic protection types), for example, by routing all traffic through the switch fabric. In some examples, switch 512 can be configured to reduce port underutilization, for example, due to network traffic loss and the need for physical intervention and the logistics of managing different client port types.
[0090] Figure 6 is a block diagram illustrating an example protection scheme including a plurality of fast optical switches AB integrated within a slow optical switch 202 , in accordance with one or more techniques of this disclosure. Figure 6 A protection scheme is shown implemented using switch 612. Switch 612 may be substantially similar to optical switch 12, switch 412, and / or switch 512 described above.
[0091] In the example shown, the protection schemes include unprotected, dual diversity, and multiple protected services. In the example shown, there are two protection levels for three different speeds, resulting in six protection groups, e.g., protection groups 1-6. Although two protection levels and three speeds are shown, this is merely exemplary, and the present disclosure contemplates fewer or more protection levels and / or speeds, e.g., one protection level or three or more protection levels and / or one or two speeds or four or more speeds.
[0092] In the example shown, client traffic having a first protection level is routed to DCI A through fast switch A, while client traffic having a second protection level is routed to DCI B through fast switch B. Client traffic having a first speed is routed through fast switch A ports and fast switch B ports, as shown by speed grouping 670, client traffic having a second speed is routed through fast switch A ports and fast switch B ports, as shown by speed grouping 672, and client traffic having a third speed is routed through fast switch A ports and fast switch B ports, as shown by speed grouping 676. In some examples, the first speed may be 100-800G DWDM, the second speed may be 100-400G DWDM, and the third speed may be 100-200G DWDM, although the present disclosure contemplates any suitable speed for any of the first, second, and third speeds.
[0093] In the example shown, the dashed lines represent reconfigurable optical cross-connects routed through slow switch 202. For example, if a portion or all of fast switch A or fast switch B, or some other resource in the path through switch 612 fails, any of the protection groups 1-6, the dual diversity groups, and / or the unprotected groups may be rerouted via reconfiguration through the slow optical switch.
[0094] In the illustrated example, the flexible grid systems 662 and 664 are integrated within the slow switch 202. In the illustrated example, within the flexible grid system 662, the client traffic that has been organized and converted to DWDM wavelengths is multiplexed / demultiplexed using an add / drop multiplexer / demultiplexer 650. The channels pass through a fiber recombination panel 654. The channels then pass through a reconfigurable optical add / drop multiplexer (ROADM) 652 and an amplifier 656, such as an erbium doped fiber amplifier (EDFA) 656. In some examples, the channels then exit the switch 612 as a DWDM signal 680 with a first protection level and a DWDM signal 682 with a second protection level. In some examples, the DWDM signal 680 and / or the DWDM signal 682 can enter the switch 612 and be redirected to different paths outside of the physical fiber equipment. The DWDM signal 680 can be a working optical path, while the DWDM signal 682 can be a diversified optical path. In some examples, multiplexer / demultiplexer 650 may be a colorless, non-directional, and / or contention-free (eg, CD or CDC) filter.
[0095] In the illustrated example, within the flexible grid ROADM system 664, client traffic can be multiplexed / demultiplexed using optical array waveguide routers (AWGs) through ROADM 652 and amplifiers 658. In some examples, the channels then exit the switch 612 as DWDM signals 684 and DWDM signals 682, and the DWDM signals 684 and 686 can be optical paths external to the physical fiber plant. In some examples, the DWDM signal 684 and / or the DWDM signal 686 can enter the switch 612 and be redirected to different paths external to the physical fiber plant.
[0096] In some examples, switch 612 can be configured to reroute a client from one channel to another, for example, to improve and / or optimize line-side traffic. For example, as shown, the client side is mapped to the line-side (DWDM) side in the optical network. Due to traffic loss and the difference between actual traffic growth and expected traffic growth, the line side (routing and channel allocation) may become suboptimal over time. Switch 612 can be configured to provide load balancing through the network to alleviate congestion on certain links, provide spectrum optimization to alleviate spectrum congestion in the network, and provide solutions for temporary interruptions, such as network upgrades, card changes, etc., to reduce and / or minimize interruptions. Switch 612 can be configured to support spectrum reallocation, regeneration and / or wavelength conversion, and partial addition / deletion in AWG-based networks.
[0097] In some examples, switch 612 can be configured to support dynamic and / or time-varying capacity allocation. For example, nodes / degrees can be configured for maximum total capacity, and switch 612 can be configured to enable a first customer to sell capacity to a second customer in short time increments. Switch 612 can be configured to enable such sales by identifying required network resources and completing lightpaths. Thus, switch 612 can be configured to support time-varying demand on a packet network, where switch ports can be reallocated to meet paths with high demand to improve latency and alleviate congestion, as well as time-dependent services such as backup, data migration, etc.
[0098] In some examples, switch 612 can be configured to enable seamless network upgrades, additions, deletions, and expansions in a disaggregated network architecture. For example, switch 612 can enable control migration from an optical network provider to a data center transport software defined network controller (T-SDN controller), for example, making the optical network more vendor agnostic. Switch 612 can be configured to reuse existing customer demarcation ports with old service interfaces and automatically configure ports to carry new service interfaces, for example, from 10E to 16G GC or from 10GRE to 400GE, etc. Switch 612 can be configured to provide fast turnaround service activation for on-demand services using a variety of interfaces and protection types.
[0099] In some examples, the switch 612 can be configured to detect faults in transmission and reception equipment (e.g., repeaters and layer 1 / 2 / 3 switches), line equipment (ROADM / AMP / Mux / Demux), and optical fibers, and perform calculations and reroute client signals from failed equipment and paths to normal working equipment and paths. The switch 612 can be configured to quickly switch client signals from a failed transmitter / receiver module (e.g., repeaters and layer 1 / 2 / 3 switches), line equipment (ROADM), optical fiber, or optical path to another normal working transmitter / receiver module, line equipment, and / or optical fiber path. In some examples, the switch 612 can include a controller (not shown) and / or a software control mechanism that is configured to dynamically configure / reconfigure, coordinate, and recalculate switch states and positions across multiple data centers and locations based on an optimized network path automatically calculated as feedback from a path calculation engine, and / or arbitrate multiple types of clients, client traffic rates, formats, and match clients with appropriate DWDM modules.
[0100] Figure 7 is a block diagram illustrating additional details of one example of a computing device that operates in accordance with one or more techniques of this disclosure. Figure 7 A specific example of a server or other computing device 500 may be shown that includes one or more processors 502 for executing any one or more of the PNP 3 or any other computing device described herein. Other examples of computing device 500 may be used in other situations. Although Figure 7 A standalone computing device 500 is shown for example, but the computing device may be any component or system including one or more processors or other computing environment suitable for executing software instructions, and does not necessarily need to include, for example Figure 7 506; and in some examples, components such as storage device 508 may not be co-located or located in the same chassis as other components.
[0101] like Figure 7As shown in the specific example of , the computing device 500 includes one or more processors 502, one or more input devices 504, one or more communication units 506, one or more output devices 512, one or more storage devices 508, a user interface (UI) device 510, and a communication unit 506. In one example, the computing device 500 also includes one or more applications 522, (multiple) programmable network platform applications 524, and an operating system 516 that can be executed by the computing device 500. Each of the components 502, 504, 506, 508, 510, and 512 is coupled (physically, communicatively, and / or operationally) for inter-component communication. In some examples, the communication channel 514 may include a system bus, a network connection, an inter-process communication data structure, or any other method for communicating data. As an example, the components 502, 504, 506, 508, 510, and 512 may be coupled via one or more communication channels 514.
[0102] In one example, processor 502 is configured to implement functions and / or process instructions for execution within computing device 500. For example, processor 502 may be capable of processing instructions stored in storage device 508. Examples of processor 502 may include any one or more of the following: a microprocessor, a controller, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), or equivalent discrete or integrated logic circuitry.
[0103] One or more storage devices 508 may be configured to store information within the computing device 500 during operation. In some examples, the storage device 508 is described as a computer-readable storage medium. In some examples, the storage device 508 is a temporary memory, which means that the primary purpose of the storage device 508 is not long-term storage. In some examples, the storage device 508 is described as a volatile memory, which means that the storage device 508 does not retain the stored contents when the computer is turned off. Examples of volatile memory include random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), and other forms of volatile memory known in the art. In some examples, the storage device 508 is used to store program instructions executed by the processor 502. In one example, the storage device 508 is used by software or applications running on the computing device 500 to temporarily store information during program execution.
[0104] In some examples, storage device 508 also includes one or more computer-readable storage media. Storage device 508 can be configured to store a larger amount of information than volatile memory. Storage device 508 can also be configured for long-term storage of information. In some examples, storage device 508 includes a non-volatile storage element. Examples of such non-volatile storage elements include a magnetic hard disk, an optical disk, a floppy disk, a flash memory, or an electrically programmable memory (EPROM) or an electrically erasable programmable (EEPROM) memory.
[0105] In some examples, the computing device 500 also includes one or more communication units 506. In one example, the computing device 500 uses the communication unit 506 to communicate with external devices via one or more networks (such as one or more wired / wireless / mobile networks). The communication unit 506 may include a network interface card (such as an Ethernet card), an optical transceiver, a radio frequency transceiver, or any other type of device that can send and receive information. Other examples of such network interfaces may include 3G and WiFi radios. In some examples, the computing device 500 uses the communication unit 506 to communicate with external devices.
[0106] In one example, computing device 500 also includes one or more user interface devices 510. In some examples, user interface device 510 is configured to receive input from a user through tactile, audio, or video feedback. Examples of (multiple) user interface devices 510 include a presence-sensitive display, a mouse, a keyboard, a voice response system, a camera, a microphone, or any other type of device for detecting commands from a user. In some examples, the presence-sensitive display includes a touch screen.
[0107] One or more output devices 512 may be included in computing device 500. In some examples, output device 512 is configured to provide output to a user using tactile, audio, or video stimulation. In one example, output device 512 includes a presence-sensitive display, a sound card, a video graphics adapter card, or any other type of device for converting signals into an appropriate form understandable to a human or machine. Other examples of output device 512 include a speaker, a cathode ray tube (CRT) display, a liquid crystal display (LCD), or any other type of device capable of generating understandable output to a user.
[0108] Computing device 500 can include operating system 516. In some examples, operating system 516 controls the operation of components of computing device 500. For instance, in one example, operating system 516 facilitates communication of one or more application programs 522 and programmable network platform application(s) 524 with processor 502, communication unit 506, storage device 508, input device 504, user interface device 510, and output device 512.
[0109] Applications 522 and programmable network platform application(s) 524 may also include program instructions and / or data that may be executed by computing device 500. Example programmable network platform application(s) 524 that may be executed by computing device 500 may include one or more of a coordination engine module, an API gateway module, and a subsystem; or in the illustrated architecture, a fiber cross-connect configuration engine 550 or an optical fabric configuration engine 552, each of which is shown in dashed lines to indicate that these engines may or may not be executed by any given computing device 500 example.
[0110] The optical fiber cross-connect configuration engine 550 may include instructions for causing the computing device 500 to perform one or more of the operations and actions described in the present disclosure regarding configuring an optical cross-connect with any of the switches 12, 312, 412, 512, and 612. The optical fabric configuration engine 552 may include instructions for causing the computing device 500 to perform one or more of the operations and actions described in the present disclosure regarding using the optical of any of the switches 12, 312, 412, 512, and 612.
[0111] Figure 8 is a flow chart of an example operating mode of an optical switch in accordance with one or more techniques of this disclosure. Figure 8 about Figure 6 The optical switch 612, the slow switch 202, the fast switches A and B, and Figure 2A . However, Figure 8 The example techniques of may be used with other switches and controllers, such as any of switches 12 , 312 , 412 , and / or 512 .
[0112] The controller may detect a fault in a first DCI connected to a first output port of an optical switch (802). For example, the controller may detect a fault and / or failure in a transmission and receiving device (e.g., a repeater and a layer 1 / 2 / 3 switch), a line device (ROADM / AMP / Mux / Demux), or an optical fiber.
[0113] The controller may output configuration data to configure a fast optical switch of the optical switch to switch from a first output port of the optical switch connected to the first data center interconnect to a second output port of the optical switch connected to the second data center interconnect (804). For example, the controller may quickly switch client signals from a failed transmitter / receiver module (e.g., a transponder and layer 1 / 2 / 3 switch, line equipment (ROADM), optical fiber, or optical path) to another properly functioning transmitter / receiver module, line equipment, and / or optical fiber path.
[0114] This article describes the following examples.
[0115] Example 1: An optical switch comprising:
[0116] Multiple input ports and multiple output ports;
[0117] a cross-connect structure having one or more inputs, one or more outputs and means for selectively cross-connecting said inputs with said outputs;
[0118] An integrated fast optical switch includes a first input, a first output, and a second output.
[0119] wherein the first input is connected to a first one of the outputs of the cross-connect structure, and
[0120] The switching time of the integrated fast optical switch is less than the switching time of the cross-connect structure to switch the first input between the first output on a path to a first output port among the multiple output ports and the second output on a path to the second output port among the multiple output ports.
[0121] Example 2: The optical switch according to Example 1,
[0122] wherein the first output of the fast optical switch is connected to a first input of the one or more inputs of the cross-connect structure, and
[0123] The second output of the fast optical switch is connected to a different second input of the one or more inputs of the cross-connect structure.
[0124] Example 3: The optical switch of Example 1 or 2, wherein the cross-connect structure is configured with an optical cross-connect from one of the one or more inputs to one of the one or more outputs that bypasses the fast optical switch.
[0125] Example 4: An optical switch according to any one of Examples 1 to 3, wherein the cross-connect structure is configured with at least one redundant optical cross-connect, the at least one redundant optical cross-connect corresponding to at least one optical cross-connect configured in the fast optical switch, wherein the at least one redundant optical cross-connect bypasses the fast optical switch.
[0126] Example 5: The optical switch of any of Examples 1 to 4, wherein the fast optical switch is configured to switch optical cross-connects via beam steering.
[0127] Example 6: The optical switch of any one of Examples 1 to 5, wherein the fast optical switch is configured to switch a plurality of optical cross-connects simultaneously.
[0128] Example 7: An optical switch according to any one of Examples 1 to 6, wherein the fast optical switch is a first fast optical switch, the first fast optical switch includes a switching time of less than 1000 milliseconds, and the optical switch further includes: a second integrated fast optical switch, including a switching time of less than 1000 milliseconds, wherein the second fast optical switch provides redundancy for the first fast optical switch.
[0129] Example 8: An optical switch according to Example 7, wherein the respective inputs of the first fast optical switch and the second fast optical switch are configured to be connected to at least one output port of the cross-connection structure, wherein the first output and the second output of the first fast optical switch are connected to at least one input port of the cross-connection structure, and wherein each output of the second fast optical switch is connected to at least one input port of the cross-connection structure.
[0130] Example 9: The optical switch of Example 8, wherein the cross-connect structure is configured to maintain at least one first redundant optical cross-connect corresponding to at least one optical cross-connect maintained by the first fast optical switch, wherein the at least one redundant optical cross-connect bypasses the first fast optical switch,
[0131] The cross-connect structure is configured to maintain at least one second redundant optical cross-connect corresponding to the at least one optical cross-connect maintained by the second fast optical switch, wherein the at least one redundant optical cross-connect bypasses the second fast optical switch.
[0132] Example 10: The optical switch according to any one of Examples 1 to 9,
[0133] wherein a second one of the outputs of the cross-connect structure is directly connected to a third one of the plurality of output ports,
[0134] The cross-connect structure can be configured to switch from the first output of the outputs of the cross-connect structure and the second output of the outputs of the cross-connect structure to bypass the fast optical switch.
[0135] Example 11: The optical switch of any of Examples 1 to 10, wherein the path to the first output port of the plurality of output ports comprises a path through the cross-connect structure.
[0136] Example 12: The optical switch of any one of Examples 1 to 11, wherein the fast optical switch comprises a photonic switch.
[0137] Example 13: An interconnection system comprising:
[0138] First Data Center Interconnect;
[0139] Different second data centers are interconnected;
[0140] Optical switch, including:
[0141] Multiple input ports and multiple output ports;
[0142] a cross-connect structure having one or more inputs, one or more outputs, and an automated mechanism for cross-connecting the inputs to the outputs;
[0143] An integrated fast optical switch comprises a first input, a first output and a second output, wherein the first input is connected to the first output of the outputs of the cross-connect structure, and
[0144] wherein the fast optical switch has a switching time of less than 1000 milliseconds to switch the first input between the first output on a path to a first output port among the plurality of output ports and the second output on a path to a second output port among the plurality of output ports,
[0145] wherein the first output port of the plurality of output ports is connected to the first data center interconnect, and
[0146] Wherein the second output port of the plurality of output ports is connected to the second data center interconnect.
[0147] Example 14: The interconnect system of Example 13, further comprising:
[0148] A wiring panel including the optical switch.
[0149] Example 15: The interconnect system of Example 13 or 14, further comprising:
[0150] A controller includes processing circuitry and is configured to output configuration data to configure the optical switch to cause the fast optical switch to switch from the first output to the second output.
[0151] Example 16: The interconnect system of any one of Examples 13 to 15, further comprising:
[0152] A controller includes processing circuitry and is configured to output configuration data to configure the optical switch in response to determining that the first data center interconnect has failed to cause the fast optical switch to switch from the first output to the second output.
[0153] Example 17: A controller comprising:
[0154] processing circuitry coupled to the memory, the processing circuitry and memory configured to control an optical switch, the optical switch comprising:
[0155] Multiple input ports and multiple output ports;
[0156] a cross-connect structure having one or more inputs, one or more outputs, and an automated mechanism for cross-connecting the inputs to the outputs;
[0157] An integrated fast optical switch comprises a first input, a first output and a second output, wherein the first input is connected to the first output of the outputs of the cross-connect structure, and
[0158] The fast optical switch has a switching time of less than 1000 milliseconds to switch the first input between the first output on a path to a first output port among the plurality of output ports and a second output on a path to a second output port among the plurality of output ports.
[0159] Example 18: A controller according to Example 17, wherein the processing circuit system and memory are configured to allocate inputs and outputs of the cross-connect structure and the fast optical switch to form an optical sub-network, the optical sub-network including at least one optical cross-connect capable of being switched by reconfiguring the fast optical switch.
[0160] Example 19: The controller of Example 17 or 18, wherein the controller is configured to reallocate at least one optical cross-connect of the sub-network to at least one redundant optical cross-connect that bypasses the fast optical switch.
[0161] Example 20: A method comprising:
[0162] detecting, by a controller of an optical switch, a failure of a first data center interconnect connected to a first output port of the optical switch; and
[0163] In response to detecting the failure, outputting configuration data by the controller of the optical switch to configure a fast optical switch of the optical switch to switch from the first output port of the optical switch connected to the first data center interconnect to a second output port of the optical switch connected to a second data center interconnect.
[0164] The techniques described herein may be implemented in hardware, software, firmware, or any combination thereof. The various features described as modules, units, or components may be implemented together in an integrated logic device or separately as discrete but interoperable logic devices or other hardware devices. In some cases, various features of the electronic circuit system may be implemented as one or more integrated circuit devices, such as an integrated circuit chip or chipset.
[0165] If implemented in hardware, the present disclosure may be directed to an apparatus such as a processor or an integrated circuit device (such as an integrated circuit chip or chipset). Alternatively or additionally, if implemented in software or firmware, the techniques may be implemented at least in part by a computer-readable data storage medium that includes instructions that, when executed, cause the processor to perform one or more of the methods described above. For example, a computer-readable data storage medium may store such instructions for execution by a processor.
[0166] The computer-readable medium may form part of a computer program product, which may include packaging materials. The computer-readable medium may include computer data storage media, such as random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), electrically erasable programmable read-only memory (EEPROM), flash memory, magnetic or optical data storage media, etc. In some examples, an article of manufacture may include one or more computer-readable storage media.
[0167] In some examples, computer-readable storage media may include non-transitory media. The term "non-transitory" may mean that the storage medium is not contained in a carrier or propagating signal. In some examples, non-transitory storage media may store data that changes over time (e.g., in RAM or cache).
[0168] The code or instructions may be software and / or firmware, executed by a processing circuit system including one or more processors, such as one or more digital signal processors (DSPs), general-purpose microprocessors, application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other equivalent integrated or discrete logic circuit systems. Therefore, the term "processor" as used herein may refer to any of the above structures or any other structure suitable for implementing the techniques described herein. In addition, in some aspects, the functions described in the present disclosure may be provided in software modules or hardware modules.
Claims
1. An optical switch, include: Multiple input ports and multiple output ports; a cross-connect structure having one or more inputs, one or more outputs and means for selectively cross-connecting said inputs with said outputs; An integrated fast optical switch includes a first input, a first output, and a second output. wherein the first input is connected to a first one of the outputs of the cross-connect structure, and The switching time of the integrated fast optical switch is less than the switching time of the cross-connect structure to switch the first input between the first output on a path to a first output port among the multiple output ports and the second output on a path to the second output port among the multiple output ports.
2. The optical switch according to claim 1, wherein the first output of the fast optical switch is connected to a first input of the one or more inputs of the cross-connect structure, and The second output of the fast optical switch is connected to a different second input of the one or more inputs of the cross-connect structure.
3. The optical switch according to claim 1 or 2, wherein the cross-connect structure is configured with an optical cross-connect from one of the one or more inputs to one of the one or more outputs that bypasses the fast optical switch.
4. The optical switch according to any one of claims 1 to 3, wherein the cross-connection structure is configured with at least one redundant optical cross-connection, the at least one redundant optical cross-connection corresponding to at least one optical cross-connection configured in the fast optical switch, wherein the at least one redundant optical cross-connection bypasses the fast optical switch.
5. The optical switch according to any one of claims 1 to 4, wherein the fast optical switch is configured to switch optical cross-connections via beam steering.
6. The optical switch according to any one of claims 1 to 5, wherein the fast optical switch is configured to switch a plurality of optical cross-connects simultaneously.
7. The optical switch according to any one of claims 1 to 6, wherein the fast optical switch is a first fast optical switch, the first fast optical switch comprising a switching time of less than 1000 milliseconds, the optical switch further comprising: include: The second integrated fast optical switch, including a switching time of less than 1000 milliseconds, The second fast optical switch provides redundancy for the first fast optical switch.
8. The optical switch of claim 7, wherein respective inputs of the first fast optical switch and the second fast optical switch are configured to be connected to at least one output port of the cross-connect structure, wherein the first output and the second output of the first fast optical switch are connected to at least one input port of the cross-connect structure, and wherein each output of the second fast optical switch is connected to at least one input port of the cross-connect structure.
9. The optical switch of claim 8, wherein the cross-connect structure is configured to maintain at least one first redundant optical cross-connect corresponding to at least one optical cross-connect maintained by the first fast optical switch, wherein the at least one redundant optical cross-connect bypasses the first fast optical switch, The cross-connect structure is configured to maintain at least one second redundant optical cross-connect corresponding to the at least one optical cross-connect maintained by the second fast optical switch, wherein the at least one redundant optical cross-connect bypasses the second fast optical switch.
10. The optical switch according to any one of claims 1 to 9, wherein a second one of the outputs of the cross-connect structure is directly connected to a third one of the plurality of output ports, The cross-connect structure can be configured to switch from the first output of the outputs of the cross-connect structure and the second output of the outputs of the cross-connect structure to bypass the fast optical switch.
11. The optical switch of any one of claims 1 to 10, wherein the path to the first output port of the plurality of output ports comprises a path through the cross-connect structure.
12. The optical switch according to any one of claims 1 to 11, wherein the fast optical switch comprises a photonic switch.
13. An interconnection system, include: First Data Center Interconnect; Different second data centers are interconnected; Optical switch, including: Multiple input ports and multiple output ports; a cross-connect structure having one or more inputs, one or more outputs, and an automated mechanism for cross-connecting the inputs to the outputs; An integrated fast optical switch includes a first input, a first output, and a second output. wherein the first input is connected to a first one of the outputs of the cross-connect structure, and wherein the fast optical switch has a switching time of less than 1000 milliseconds to switch the first input between the first output on a path to a first output port among the plurality of output ports and the second output on a path to a second output port among the plurality of output ports, wherein the first output port of the plurality of output ports is connected to the first data center interconnect, and Wherein the second output port of the plurality of output ports is connected to the second data center interconnect.
14. The interconnection system according to claim 13, further comprising: include: A wiring panel including the optical switch.
15. The interconnection system according to claim 13 or 14, further comprising: include: A controller includes processing circuitry and is configured to output configuration data to configure the optical switch to cause the fast optical switch to switch from the first output to the second output.
16. The interconnection system according to any one of claims 13 to 15, further comprising: include: A controller includes processing circuitry and is configured to output configuration data to configure the optical switch in response to determining that the first data center interconnect has failed to cause the fast optical switch to switch from the first output to the second output.
17. A controller, include: processing circuitry coupled to the memory, the processing circuitry and memory configured to control an optical switch, the optical switch comprising: Multiple input ports and multiple output ports; a cross-connect structure having one or more inputs, one or more outputs, and an automated mechanism for cross-connecting the inputs to the outputs; An integrated fast optical switch includes a first input, a first output, and a second output. wherein the first input is connected to a first one of the outputs of the cross-connect structure, and The fast optical switch has a switching time of less than 1000 milliseconds to switch the first input between the first output on a path to a first output port among the plurality of output ports and a second output on a path to a second output port among the plurality of output ports.
18. The controller of claim 17, wherein the processing circuitry and memory are configured to allocate inputs and outputs of the cross-connect structure and the fast optical switch to form an optical sub-network comprising at least one optical cross-connect that can be switched by reconfiguring the fast optical switch.
19. The controller according to claim 17 or 18, wherein the controller is configured to reallocate at least one optical cross-connect of the sub-network to at least one redundant optical cross-connect bypassing the fast optical switch.
20. A method, include: detecting, by a controller of an optical switch, a failure of a first data center interconnect connected to a first output port of the optical switch; as well as In response to detecting the failure, outputting configuration data by the controller of the optical switch to configure a fast optical switch of the optical switch to switch from the first output port of the optical switch connected to the first data center interconnect to a second output port of the optical switch connected to a second data center interconnect.
